HWD-YOLO:A New Vision-Based Helmet Wearing Detection Method

It is crucial to ensure workers wear safety helmets when working at a workplace with a high risk of safety accidents,such as construction sites and mine tunnels.Although existing methods can achieve helmet detection in images,their accuracy and speed still need improvements since complex,cluttered,and large-scale scenes of real workplaces cause server occlusion,illumination change,scale variation,and perspective distortion.So,a new safety helmet-wearing detection method based on deep learning is proposed.Firstly,a new multi-scale contextual aggregation module is proposed to aggregate multi-scale feature information globally and highlight the details of concerned objects in the backbone part of the deep neural network.Secondly,a new detection block combining the dilate convolution and attention mechanism is proposed and introduced into the prediction part.This block can effectively extract deep featureswhile retaining information on fine-grained details,such as edges and small objects.Moreover,some newly emerged modules are incorporated into the proposed network to improve safety helmetwearing detection performance further.Extensive experiments on open dataset validate the proposed method.It reaches better performance on helmet-wearing detection and even outperforms the state-of-the-art method.To be more specific,the mAP increases by 3.4%,and the speed increases from17 to 33 fps in comparison with the baseline,You Only Look Once(YOLO)version 5X,and themean average precision increases by 1.0%and the speed increases by 7 fps in comparison with the YOLO version 7.The generalization ability and portability experiment results show that the proposed improvements could serve as a springboard for deep neural network design to improve object detection performance in complex scenarios.

Microstructure and Wear/corrosion Resistance of Stainless Steel Laser-alloyed with Mn+W_(2)C, Mn+NiWC and Mn+SiC

In-situ formed high Mn steel coating reinforced by carbides was formed by laser surface alloying(LSA).Laser alloyed layers on 1Cr18Ni9Ti steel with Mn+W_(2)C(specimen A),Mn+NiWC(specimen B)and Mn+SiC(specimen C)powders were fabricated to improve the wear and corrosion behavior of 1Cr18Ni9Ti steel blades in high speed mixers.Microstructure evolution,phases,element distribution,microhardness,wear and corrosion behavior of the laser alloyed layers were investigated.Results indicated that high Mn steel matrix composites with undissolved W_(2)C,WC and other in-situ formed carbides were formed by LSA with Mn+W_(2)C and Mn+NiWC while SiC totally dissolved into the high Mn matrix when adding Mn+SiC.Ni as the binding phase in Ni-WC powder decreased the crack sensitivity of the alloyed layer as compared with the addition of W_(2)C powder.An improvement in average microhardness was achieved in the matrix in specimen A,B and C,with the value of 615,602 and 277 HV_(0.5),while that of the substrate was 212 HV_(0.5).The increase of microhardness,wear and corrosion resistance is highly corelated to microstructure,formed phases,type and content of carbides,micro-hardness and toughness of the alloyed layers.

Abrasive wear behavior of functionally graded Al_(3)Ti reinforced aluminum matrix composite

Aluminum alloys are widely used in industry due to their light weight.These alloys are generally exposed to abrasive wear,which diminishes their effective lifespan.The wear resistance of these alloys is enhanced by adding various reinforcements,however,this enhancement comes at the cost of reduced fracture toughness.This paradox of increased wear resistance versus decreased fracture toughness in aluminum alloys can be resolved by using functionally graded materials (FGMs).This study focuses on the abrasive wear behavior of functional graded aluminum matrix composites reinforced with Al_(3)Ti particles.The wear properties of the composites were investigated by considering the characteristics of the composite such as matrix type and various composite zones,as well as the wear parameters such as abrasive particle diameter,load,sliding speed and distance.Taguchi method was used in the abrasive wear tests in order to get more reliable results in a timeefficient manner.Experiment recipes were created based on the L_(27)(3^(6)) orthogonal series.As a result of the study,it is observed that the wear resistance of the composites increases with an increase in Al_(3)Ti reinforcement content and hardness of the matrix.In addition,the size of abrasive particles and the applied load are significant factors affecting abrasive wear.

Thermal effects on wear behavior of additively manufactured NiTi shape memory alloys

NiTi alloys fabricated by laser powder bed fusion(LPBF)additive manufacturing technology not only address the compositional instability resulting from complex processes but also solve the challenges of difficult machining of intricate aerospace structures.However,there are very few reports on the wear behavior of LPBF-NiTi alloys.In the present work,the effects of microstructure and thermal treatment,including heat treatment and frictional heat,on the wear behavior of LPBF-NiTi alloy and 100Cr6 ball were analyzed through a series of tribological experiments with different sliding speeds.As the average sliding speed increases(0.079–0.216 m/s),the wear rate of the as-built and heat-treated samples tends to decrease in the range of 2.69×10^(-3)–0.97×10^(-3)mm^(3)/m.Although the heat-treated LPBF-NiTi alloy is 46%harder than the as-built alloy is,the latter has a higher toughness(505 MJ/m^(3))and greater transformation strain of SIM(0.097).This leads to a coupling effect of heat treatment and sliding speed on the wear resistance.In addition,the wear track morphologies under different sliding speeds are asymmetric due to the 24% greater acceleration at the far end from the motor and the 2.15 mm deviation between the maximum speed position and the geometric center of the track.The wear modes of the as-built and heat-treated samples included adhesive,abrasive and delamination wear.Moreover,the wear morphologies and dominant wear modes change with the frictionally caused heat release induced by the sliding speed.

Wearing resistance of in-situ Al-based composites with different SiO_2/C/Al molar ratios fabricated by reaction hot pressing

The in-situ Al-based composites with different SiO2/C/Al molar ratios were fabricated by reaction hot pressing. The dry sliding wear characteristics of the composites were investigated using a pin-on-disc wear tester. Scanning electron microscopy (SEM) and energy dispersive X-ray spectroscopy (EDX) were used to investigate the surface composition and its morphology. The results show that when the SiO2/C/Al molar ratio is 3:6:9, more in-situ synthesized Al2O3 and SiC along with Si particles are produced, and Al4C3 is prevented completely from the Al?SiO2?C system. Thereby, a significant improvement of wear resistance is obtained. When the sliding velocity increases from 0.4 to 1.6 m/s, the wear loss decreases gradually. With increasing the normal load, the wear loss increases as well. Ploughing, craters and micro-grooving are observed as dominant abrasive wear mechanisms. Whereas, when a high velocity is employed, only the oxidation mechanism controls the wear behavior of the composites.

WEARING PERFORMANCE OF STEEL BALLS IN WET GRINDING

ＩＮＴＲＯＤＵＣＴＩＯＮＳｔｅｅｌｂａｌｓａｎｄｓｔｅｌｒｏｄｓａｒｅｔｗｏｍａｉｎｋｉｎｄｓｏｆｇｒｉｎｄｉｎｇｍｅｄｉｕｍ，ｂｕｔｉｎｐｒａｃｔｉｃｅｔｈｅｓｔｅｅｌｂａｌｓａｒｅｍｏｒｅｗｉｄｅｌｙｕｓｅｄｔｈａｎｓｔｅｌｒｏｄｓ［１］．Ｔｏｓ...

Design of Balanced Reactor Welded with Water-Cooled Aluminum Busbars

A new process of welding aluminum water-cooled busbars is proposed, It can not only reduce the weight and cost, but also improve the dynamic and thermal stability. Furthermore~ both finite element method analysis and a prototype test testify the advantages of the design which is not limited by load current and provides a new approach for water-cooled reactors.

Analysis and optimization of heat loss for water-cooled furnace roller

A heat transfer model of furnace roller cooling process was established based on analysis of furnace roller＇s structure. The complicated model was solved with iteration planning algorithm based on Newton search. The model is proved logical and credible by comparing calculated results and measured data. Then, the relationship between water flow velocity, inlet water temperature, furnace temperature and roller cross section temperature, outlet water temperature, water temperature rise, cooling water heat absorption was studied. The conclusions and recommendations are mainly as follows： l） Cooling water temperature rise decreases with the increase of water flow velocity, but it has small relationship with inlet water temperature; 2） In order to get little water scale, inlet water temperature should be controlled below 30 ℃. 3） The cooling water flow velocity should be greater than critical velocity. The critical velocity is 0.07 m/s and water flow velocity should be controlled within 0.4-0.8 m/s. Within this velocity range, water cooling efficiency is high and water temperature rise is little. If cooling water velocity increases again, heat loss will increase, leading to energy wasting.

Real-time Safety Helmet-wearing Detection Based on Improved YOLOv5

Safety helmet-wearing detection is an essential part of the intelligentmonitoring system. To improve the speed and accuracy of detection, especiallysmall targets and occluded objects, it presents a novel and efficient detectormodel. The underlying core algorithm of this model adopts the YOLOv5 (YouOnly Look Once version 5) network with the best comprehensive detection performance. It is improved by adding an attention mechanism, a CIoU (CompleteIntersection Over Union) Loss function, and the Mish activation function. First,it applies the attention mechanism in the feature extraction. The network can learnthe weight of each channel independently and enhance the information dissemination between features. Second, it adopts CIoU loss function to achieve accuratebounding box regression. Third, it utilizes Mish activation function to improvedetection accuracy and generalization ability. It builds a safety helmet-wearingdetection data set containing more than 10,000 images collected from the Internetfor preprocessing. On the self-made helmet wearing test data set, the averageaccuracy of the helmet detection of the proposed algorithm is 96.7%, which is1.9% higher than that of the YOLOv5 algorithm. It meets the accuracy requirements of the helmet-wearing detection under construction scenarios.

Numerical Simulation on Subcooled Boiling Heat Transfer Characteristics of Water-Cooled W/Cu Divertors

In order to realize safe and stable operation of a water-cooled W/Cu divertor under high heating condition,the exact knowledge of its subcooled boiling heat transfer characteristics under different design parameters is crucial.In this paper,subcooled boiling heat transfer in a water-cooled W/Cu divertor was numerically investigated based on computational fluid dynamic（CFD）.The boiling heat transfer was simulated based on the Euler homogeneous phase model,and local differences of liquid physical properties were considered under one-sided high heating conditions.The calculated wall temperature was in good agreement with experimental results,with the maximum error of 5%only.On this basis,the void fraction distribution,flow field and heat transfer coefficient（HTC）distribution were obtained.The effects of heat flux,inlet velocity and inlet temperature on temperature distribution and pressure drop of a water-cooled W/Cu divertor were also investigated.These results provide a valuable reference for the thermal-hydraulic design of a water-cooled W/Cu divertor.

Prediction models of burst strength degradation for casing with considerations of both wear and corrosion

Casing wear and casing corrosion are serious problems affecting casing integrity failure in deep and ultra-deep wells.This paper aims to predict the casing burst strength with considerations of both wear and corrosion.Firstly,the crescent wear shape is simplified into three categories according to common mathematical models.Then,based on the mechano-electrochemical(M-E)interaction,the prediction model of corrosion depth is built with worn depth as the initial condition,and the prediction models of burst strength of the worn casing and corroded casing are obtained.Secondly,the accuracy of different prediction models is validated by numerical simulation,and the main influence factors on casing strength are obtained.At last,the theoretical models are applied to an ultra-deep well in Northwest China,and the dangerous well sections caused by wear and corrosion are predicted,and the corrosion rate threshold to ensure the safety of casing is obtained.The results show that the existence of wear defects results in a stress concentration and enhanced M-E interaction on corrosion depth growth.The accuracy of different mathematical models is different:the slot ring model is most accurate for predicting corrosion depth,and the eccentric model is most accurate for predicting the burst strength of corroded casing.The burst strength of the casing will be overestimated by more than one-third if the M-E interaction is neglected,so the coupling effect of wear and corrosion should be sufficiently considered in casing integrity evaluation.

Wearing Property and Friction Mechanism of Ceramic Side Dams Used in Thin Strip Continuous Casting

In this paper,based on three different kinds of ceramic side dams for thin strip antinuous casting,the friction and wearing property were studied.The effects of friction pressure,temperature and friction time on the friction and wearing property of the ceramic side dam were researched.What’s more,the friction mechanism and wearing mechanism of the ceramic side dam were researched as well.Results show that the ceramic side dam of BN-SiA lO N has the best wearing resistance property.while at room temperature,16 min of friction time and0.35 MPa of friction pressure,the test friction coefficient is 0.60 and wearing capacity is 272.358 mm-3.In addition,when at 400℃,16 min of friction time and 0.18MPa of friction pressure,the test friction coefficient is0.70.The friction mechanism of ceramic side dam with the opposite wearing material is mainly the composite wear of adhesion,abrasive and fatigue.

Preparation of Al-Zn-Mg-Cu alloy semisolid slurry through a water-cooled serpentine pouring channel

The semisolid slurry of Al-Zn-Mg-Cu alloy was prepared through a self-designed water-cooled copper serpentine pouring channel(WSPC) machine. Influences of pouring temperature, the number of turns and the cooling water flow rate on the microstructure of the semisolid Al-Zn-Mg-Cu alloy slurry were investigated. The results show that the semisolid Al-Zn-Mg-Cu alloy slurry with satisfactory quality can be generated by the WSPC when the pouring temperature is in the range between 680 ℃ and 700 ℃. At a given pouring temperature, the average grain size of primary α-Al decreases and the shape factor increases with the increase of the number of turns. When the cooling water flow rate is 450 L·h^(-1), the obtained semisolid slurry is optimal. During the preparation of the semisolid Al-Zn-Mg-Cu alloy slurry with low superheat pouring, the alloy melt has mixed inhibition and convection flow characteristics by "self-stirring". When the alloy melt flows through the serpentine channel, the chilling effect of the inner wall of the channel, the convection and mixed inhibition of the alloy melt greatly promote the heterogeneous nucleation and grain segregation. This effect destroys the dendrite growth mode under traditional solidification conditions, and the primary nuclei gradually evolve into spherical or nearspherical grains.

Optimization of the Water-Cooled Structure for the Divertor Plates in EAST Based on an Orthogonal Theory

An orthogoual experimental scheme was designed for optimizing a water-cooled structure of the divertor plate. There were three influencing factors： the radius R of the water- cooled pipe, and the pipe spacing L1 and L3. The influence rule of different factors on the cooling effect and thermal stress of the plate were studied, for which the influence rank was respectively R 〉 L1 〉 L3 and L3 〉 R 〉 L1. The highest temperature value decreased when R and L1 increased~ and the maximum thermal stress value dropped when R, L1 and L3 increased. The final optimized results can be summarized as： R equals 6 mm or 7 mm, L1 equals 19 mm, and L3 equals 20 mm. Compared with the initial design, the highest temperature value had a small decline~ and the maximum thermal stress value dropped by 19~ to 24~. So it was not ideal to improve the cooling effect by optimizing the geometry sizes of the water-cooled structure, even worse than increasing the flow speed, but it was very effective for dropping the maximum thermal stress value. The orthogoaal experimental method reduces the number of experiments by 80%, and thus it is feasible and effective to optimize the water-cooled structure of the divertor plate with the orthogonal theory.

Analysis of surface cracking in water-cooled rolls and heat transfer between furnace chamber and rolls in a direct flame furnace

In the direct fired furnace of a continuous annealing line, seal rolls are susceptible to deformation that leads to surface defects of steel strips. According to failure analysis, the reasons include improper structural design and heat imbalance. An improved design has been proposed to reduce stress concentration and thermal radiation. A heat transfer model has been employed to determine the proper water flow rate for roll cooling. Industrial application proves that seal rolls with the new design has less deformation and longer service life.

Research on the solid particle erosion wear of pipe steel for hydraulic fracturing based on experiments and numerical simulations

Erosion wear is a common failure mode in the oil and gas industry.In the hydraulic fracturing,the fracturing pipes are not only in high-pressure working environment,but also suffer from the impact of the high-speed solid particles in the fracturing fluid.Beneath such complex conditions,the vulnerable components of the pipe system are prone to perforation or even burst accidents,which has become one of the most serious risks at the fracturing site.Unfortunately,it is not yet fully understood the erosion mechanism of pipe steel for hydraulic fracturing.Therefore,this article provides a detailed analysis of the erosion behavior of fracturing pipes under complex working conditions based on experiments and numerical simulations.Firstly,we conducted erosion experiments on AISI 4135 steel for fracturing pipes to investigate the erosion characteristics of the material.The effects of impact angle,flow velocity and applied stress on erosion wear were comprehensively considered.Then a particle impact dynamic model of erosion wear was developed based on the experimental parameters,and the evolution process of particle erosion under different impact angles,impact velocities and applied stress was analyzed.By combining the erosion characteristics,the micro-structure of the eroded area,and the micro-mechanics of erosion damage,the erosion mechanism of pipe steel under fracturing conditions was studied in detail for the first time.Under high-pressure operating conditions,it was demonstrated through experiments and numerical simulations that the size of the micro-defects in the eroded area increased as the applied stress increased,resulting in more severe erosion wear of fracturing pipes.

Fully Immersing Water-Cooled Radial Slab Laser and its Incoherent Beam Combination

A novel scheme of fully immersing water cooling is proposed for a Nd：glass radial slab laser. The slab medium is entirely immersed in the circulating water Ailing the pumping cavity, which enables much lower temperature and reasonably smaller thermal gradient in the slab medium. The radial slab is symmetrically and synchronously pumped by eight flash lamps, and produces multi-output beams with a total energy of 469md. Incoherent beam combination property of the multi-output beams is also investigated. The approach suggested here provides a way of scaling the slab lasers to much higher output levels and also a convenience for beam combinations.

Effect of Kerosene Flowing Rate on Microstructure and Wearing Properties for Fe-based Amorphous Coatings

The effects of kerosene flow rate on the microstructure and wearing properties were investigated for Fe-based amorphous coatings sprayed by High Velocity Oxygen Fuel (HVOF).The microstructures and wearing properties of the Fe-based amorphous coatings were analyzed with scanning electron microscope (SEM),X-ray diffraction analyzer (XRD),and ball-on-disc tribometer (CFT-1),respectively.The experimental results show that the well interfacial bonding can be observed between the amorphous coating layer and the substrate,and the porosity in amorphous coating layer is less to 1%.Only some crystalline a-Fe and FeO phases can be detected by XRD in the amorphous coatings,while the amorphous content is up to 99.4%.The wearing coefficient is near to 0.15,which is superior to SUS316 of 0.28.As the increasing of wearing loads,the failure mode is changed from oxidation wear to the composite of oxidation and abrasive wear.

On the viability of wearing evaluation by Thin Layer Activation in the presence of non-occupationally exposed individuals

Thin Layer Activation is a nuclear technique that has key advantages over other wear measuring techniques for mechanical systems,especially for in site experiments on equipment important to safety in nuclear plants.Still,it incurs radioactive dose and,thus,must be proved radiologically safe before use,otherwise,the utilization of this technique may be hindered inviable.Proving said technique is safe previous to any operational/monetary cost is key,providing a methodology for this early assertion is the main contribution of this work—here,only non-occupationally exposed individuals are considered.This work offers a methodology,through a case study,to ascertain the Thin Layer Activation parameters to obtain safe levels of radioactive dose while maintaining statistically reliable results.This methodology consists of using simulations,through the Monte Carlo Method,to obtain the floors and ceilings for the previously mentioned activation parameters based on operation and work conditions on site.

Prediction of Wearing of Cutting Tools Using Real Time Machining Parameters and Temperature Using Rayleigh-Ham Method

Wear of cutting tools is a big concern for industrial manufacturers, because of their acquisition cost as well as the impact on the production lines when they are unavailable. Law of wear is very important in determining cutting tools lifespan, but most of the existing models don’t take into account the cutting temperature. In this work, the theoretical and experimental results of a dynamic study of metal machining against cutting temperature of a treated steel of grade S235JR with a high-speed steel tool are provided. This study is based on the analysis of two complementary approaches, an experimental approach with the measurement of the temperature and on the other hand, an approach using modeling. Based on unifactorial and multifactorial tests (speed of cut, feed, and depth of cut), this study allowed the highlighting of the influence of the cutting temperature on the machining time. To achieve this objective, two specific approaches have been selected. The first was to measure the temperature of the cutting tool and the second was to determine the wear law using Rayleigh-Ham dimensional analysis method. This study permitted the determination of a law that integrates the cutting temperature in the calculations of the lifespan of the tools during machining.